© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 89234
    Prev
    Next
    INDEX
    Explanations

    references to commemorative plaques and dedications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carpenter
    -0.06
     elastic
    -0.06
     Ideal
    -0.06
     stuff
    -0.05
     trade
    -0.05
     Pillow
    -0.05
    Æ°á»Ľi
    -0.05
     du
    -0.05
     cease
    -0.05
     rubber
    -0.05
    POSITIVE LOGITS
    _install
    0.08
     ÎĶή
    0.08
    ignum
    0.07
    owe
    0.07
    andon
    0.07
    ipline
    0.07
    Thanks
    0.07
    ÑĢам
    0.07
    Å¡et
    0.07
    egin
    0.07
    Activations Density 0.009%

    No Known Activations